Long documents
Prompts that approach the documented context limit
GPT-5.5
GPT-5.5 has the larger documented context window.
Confidence: documented
GLM-5V-Turbo vs GPT-5.5
Updated October 20, 2026. Rank says GPT-5.5 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Share or export
Decision reading
GPT-5.5 has the higher public point estimate, 69.22 versus 49.61. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 1
- GLM-5V-Turbo only
- 1
- GPT-5.5 only
- 43
- Like-for-like categories
- 0 / 8
Estimated: GLM-5V-Turbo · Supported: GPT-5.5. Conditional ranges do not establish rank confidence.How the comparison works
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Chat turn cost
1K fresh input + 500 output tokens
GLM-5V-Turbo
GLM-5V-Turbo has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
GLM-5V-Turbo
GLM-5V-Turbo has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesCoding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
GLM-5V-Turbo is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limitedAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
GLM-5V-Turbo is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limitedCache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. GLM-5V-Turbo does not fit this workload in one request. GLM-5V-Turbo has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
Which one for a specific job
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
32.5GLM-5V-Turbo62.0GPT-5.5
Directional only · BenchAlign v5.8
GPT-5.5 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
1 GLM-5V-Turbo only
1 Shared
43 GPT-5.5 only
3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Coding
Directional only- GLM-5V-Turbo
- 32.5
- Estimated · #86/152
- GPT-5.5
- 62.0
- Supported · #14/152
- Basis
- BenchAlign v5.8 lane · 0 vs 10 public rows
- Reading
- Directional only
Knowledge
Directional only- GLM-5V-Turbo
- 45.9
- Estimated · #96/187
- GPT-5.5
- 72.1
- Supported · #15/187
- Basis
- BenchAlign v5.8 lane · 0 vs 6 public rows
- Reading
- Directional only
Instruction following
Directional only- GLM-5V-Turbo
- 74.0
- #69/149
- GPT-5.5
- 93.3
- #8/149
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Directional only
Agentic
Not comparable- GLM-5V-Turbo
- Not ranked
- GPT-5.5
- 62.7
- Supported · #23/131
- Basis
- BenchAlign v5.8 lane · 2 vs 15 public rows
- Reading
- Not comparable
Reasoning
Not comparable- GLM-5V-Turbo
- 73.3
- Unranked · 2 rankable rows
- GPT-5.5
- 70.3
- #17/27
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- GLM-5V-Turbo
- 71.7
- Unranked · 1 rankable row
- GPT-5.5
- 75.5
- #23/55
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- GLM-5V-Turbo
- Not ranked
- GPT-5.5
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- GLM-5V-Turbo
- Not ranked
- GPT-5.5
- 91.2
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
| Category | GLM-5V-Turbo | GPT-5.5 | Basis | Reading |
|---|---|---|---|---|
| Coding | 32.5Estimated · #86/152 | 62.0Supported · #14/152 | Directional onlyBenchAlign v5.8 lane · 0 vs 10 public rows | Directional only |
| Knowledge | 45.9Estimated · #96/187 | 72.1Supported · #15/187 | Directional onlyBenchAlign v5.8 lane · 0 vs 6 public rows | Directional only |
| Instruction following | 74.0#69/149 | 93.3#8/149 | Directional onlyProvisional lane · 0 vs 0 weighted rows | Directional only |
| Agentic | Not ranked | 62.7Supported · #23/131 | Not comparableBenchAlign v5.8 lane · 2 vs 15 public rows | Not comparable |
| Reasoning | 73.3Unranked · 2 rankable rows | 70.3#17/27 | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
| Multimodal | 71.7Unranked · 1 rankable row | 75.5#23/55 | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | 91.2Unranked · 3 rankable rows | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Supported evidence per lane · bars run 0–100Methodology
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- GLM-5V-Turbo
- $0.0032
- Fits in one request
- GPT-5.5
- $0.02
- Fits in one request
GLM-5V-Turbo has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- GLM-5V-Turbo
- $0.072
- Fits in one request
- GPT-5.5
- $0.34
- Fits in one request
GLM-5V-Turbo has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GLM-5V-Turbo
- $0.304
- Does not fit in one request
- Cached input priced at the published list-input rate
- GPT-5.5
- $0.5
- Fits in one request
GLM-5V-Turbo does not fit this workload in one request. GLM-5V-Turbo has no published cached-input rate, so cached tokens use its listed input rate.
Cached input falls back to the list input rate only where a cached rate is unpublished
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGLM-5V-TurboGPT-5.5
Context window
Maximum documented context; output-token limits may be lower.
GLM-5V-Turbo
200K
GPT-5.5
API model ID
GLM-5V-Turbo
Not sourced
GPT-5.5
gpt-5.5
OpenAI pricingCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GLM-5V-Turbo
Not published
GPT-5.5
$0.5 per 1M cached input tokens
OpenAI pricingDocumented inputs
GLM-5V-Turbo
Not sourced
GPT-5.5
Not sourced
Documented outputs
GLM-5V-Turbo
Not sourced
GPT-5.5
Not sourced
Provider availability
GLM-5V-Turbo
Not sourced
GPT-5.5
Not sourced
Reasoning profile
GLM-5V-Turbo
Non-Reasoning
GPT-5.5
Reasoning
Weight access
GLM-5V-Turbo
Proprietary
GPT-5.5
Proprietary
License
GLM-5V-Turbo
Proprietary
GPT-5.5
Proprietary
Release date
GLM-5V-Turbo
2026-04-02
GPT-5.5
2026-04-23
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- GPT-5.5 has the higher public point estimate, 69.22 versus 49.61. Their conditional score ranges do not overlap. These ranges do not establish rank confidence.
- Workload cost
- Repository review: $0.072 vs $0.34. Cache-heavy agent loop: $0.304 vs $0.5.
- Context tradeoff
- GPT-5.5 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, GLM-5V-Turbo or GPT-5.5?
GPT-5.5 has the higher public point estimate, 69.22 versus 49.61. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, GLM-5V-Turbo or GPT-5.5?
GPT-5.5 scores higher for coding on the public lane, 62 to 32.5. GLM-5V-Turbo is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, GLM-5V-Turbo or GPT-5.5?
GLM-5V-Turbo is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, GLM-5V-Turbo or GPT-5.5?
For the stated presets, chat costs $0.0032 on GLM-5V-Turbo and $0.02 on GPT-5.5; repository review costs $0.072 and $0.34; the cache-heavy agent loop costs $0.304 and $0.5. GLM-5V-Turbo does not fit this workload in one request. GLM-5V-Turbo has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, GLM-5V-Turbo or GPT-5.5?
GPT-5.5 has the larger documented context window: 1M, compared with 200K.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence45 rows
Agentic
Claw-Eval
GLM-5V-Turbo53.8%SourceGPT-5.5—Not directly comparable
Gert Labs
Shared sourceGLM-5V-Turbo30.76%GPT-5.572.93%GPT-5.5 leads this result
Terminal-Bench 2.0
GLM-5V-Turbo—GPT-5.582%SourceNot directly comparable
CyberGym
GLM-5V-Turbo—GPT-5.581.8%SourceNot directly comparable
BrowseComp
GLM-5V-Turbo—GPT-5.584.4%SourceNot directly comparable
OSWorld-Verified
GLM-5V-Turbo—GPT-5.578.7%SourceNot directly comparable
MCP Atlas
GLM-5V-Turbo—GPT-5.575.3%SourceNot directly comparable
Toolathlon
GLM-5V-Turbo—GPT-5.555.6%SourceNot directly comparable
τ²-bench results
GLM-5V-Turbo—GPT-5.598%SourceNot directly comparable
ResearchClawBench
GLM-5V-Turbo—GPT-5.517.0%SourceNot directly comparable
OSWorld 2.0
GLM-5V-Turbo—GPT-5.513.0%SourceNot directly comparable
JobBench
GLM-5V-Turbo—GPT-5.542.7%SourceNot directly comparable
ExploitGym
GLM-5V-Turbo—GPT-5.513.4%SourceNot directly comparable
Terminal-Bench 2.1 (Vals)
GLM-5V-Turbo—GPT-5.576.4%SourceNot directly comparable
ApprenticeBench
GLM-5V-Turbo—GPT-5.520%SourceNot directly comparable
MazeBench
GLM-5V-Turbo—GPT-5.50%SourceNot directly comparable
Coding
SWE-bench Pro
GLM-5V-Turbo—GPT-5.558.6%SourceNot directly comparable
Terminal-Bench 2.0
GLM-5V-Turbo—GPT-5.582.0%SourceNot directly comparable
Vibe Code Bench
GLM-5V-Turbo—GPT-5.569.85%SourceNot directly comparable
React Native Evals
GLM-5V-Turbo—GPT-5.584.7%SourceNot directly comparable
cursorBench31
GLM-5V-Turbo—GPT-5.559.2%SourceNot directly comparable
CursorBench 3.2
GLM-5V-Turbo—GPT-5.558.4%SourceNot directly comparable
FrontierCode 1.1 Main
GLM-5V-Turbo—GPT-5.543.0%SourceNot directly comparable
LiveCodeBench (Vals)
GLM-5V-Turbo—GPT-5.585.3%SourceNot directly comparable
SWE-bench (Vals)
GLM-5V-Turbo—GPT-5.582.6%SourceNot directly comparable
PostTrainBench v1.1
GLM-5V-Turbo—GPT-5.527.2%SourceNot directly comparable
Reasoning
MRCR v2 64K-128K
GLM-5V-Turbo—GPT-5.583.1%SourceNot directly comparable
MRCR v2 128K-256K
GLM-5V-Turbo—GPT-5.587.5%SourceNot directly comparable
ARC-AGI-2
GLM-5V-Turbo—GPT-5.585%SourceNot directly comparable
ARC-AGI-3
GLM-5V-Turbo—GPT-5.50.4%SourceNot directly comparable
ARC-AGI-1
GLM-5V-Turbo—GPT-5.595.00%SourceNot directly comparable
Multimodal
ExtractBench (LlamaIndex)
GLM-5V-Turbo—GPT-5.593.57%SourceNot directly comparable
ParseBench
GLM-5V-Turbo—GPT-5.567.76%SourceNot directly comparable
MMMU-Pro
GLM-5V-Turbo—GPT-5.581.2%SourceNot directly comparable
MMMU-Pro w/ Python
GLM-5V-Turbo—GPT-5.583.2%SourceNot directly comparable
OfficeQA Pro
GLM-5V-Turbo—GPT-5.554.1%SourceNot directly comparable
Knowledge
GPQA
GLM-5V-Turbo—GPT-5.593.6%SourceNot directly comparable
GPQA-D
GLM-5V-Turbo—GPT-5.593.6%SourceNot directly comparable
HLE
GLM-5V-Turbo—GPT-5.552.2%SourceNot directly comparable
HLE w/o tools
GLM-5V-Turbo—GPT-5.541.4%SourceNot directly comparable
GPQA Diamond (Vals)
GLM-5V-Turbo—GPT-5.593.2%SourceNot directly comparable
MMLU-Pro (Vals)
GLM-5V-Turbo—GPT-5.588.1%SourceNot directly comparable
Math
45 public results · 1 shared
Watch GLM-5V-Turbo vs GPT-5.5
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 5,600+ readers.
Last updated October 20, 2026